Skip to main content
main-content
Top

About this book

This two-volume set LNICST 286-287 constitutes the post-conference proceedings of the First EAI International Conference on Artificial Intelligence for Communications and Networks, AICON 2019, held in Harbin, China, in May 2019. The 93 full papers were carefully reviewed and selected from 152 submissions. The papers are organized in topical sections on artificial intelligence, mobile network, deep learning, machine learning, wireless communication, cognitive radio, internet of things, big data, communication system, pattern recognition, channel model, beamforming, signal processing, 5G, mobile management, resource management, wireless position.

Table of Contents

Frontmatter

Deep Learning/Machine Learning in Physical Layer and Signal Processing

Frontmatter

Dual-Mode OFDM-IM by Encoding All Possible Subcarrier Activation Patterns

In traditional orthogonal frequency division multiplexing with index modulation (OFDM-IM), when the subcarrier activation patterns (SAPs) is not a power of 2, part of SAPs will not be used. This will result in low transmission efficiency and low bit error rate (BER) performance. We have proposed a new scheme namely bit-padding dual-mode orthogonal frequency division multiplexing (BPDM-OFDM). It exploits all of the possible SAPs to convey data to obtain a better BER performance. Meanwhile, the BPDM-OFDM uses the dual-mode orthogonal frequency division multiplexing (DM-OFDM) to improve the transmission efficiency. In addition, a subcarrier interleaving technique is adopted to further improve the BER performance and the idea of hard limit algorithm, which is applied to the log-likelihood ratio detector (LLR-HL) to reduce the detection complexity. Significant performance improvement of the proposed scheme, in terms of transmission rate, detection complexity and BER performance, over the traditional OFDM-IM scheme has been validated through theoretical analysis and extensive simulations.

Xiaoping Jin, Zheng Guo, Mengmeng Zhao, Ning Jin, Dongxiao Chen

Energy Efficiency Optimization Based SWIPT in OFDM Relaying Systems

The rapid development of the information and communication industry has brought huge energy consumption, which also reduces the energy efficiency. In this article, we integrate the cooperative relaying technology into a SWIPT-OFDM system, and focus on the system energy efficiency maximization problem. More specifically, the relay node uses the DF protocol to forward information from the base station to the user. The objective function is to maximize the energy efficiency of the system, in which the system fixed circuit power consumption, target rate, and total system power limit are all considered. At first we derive a non-convex fractional expression, after a complex mathematical transformation, a new objective function is obtained, and then we propose an efficient policy to optimize the subcarrier and power allocation for obtaining the optimal energy efficiency. Simulation results show that the proposed algorithm can not only converge after several iterations, but also achieve higher energy efficiency.

Dan Huang, Weidang Lu, Mengshu Hou

An Efficient Resource Allocation Algorithm for LTE Uplink VMIMO Systems

In this paper, we focus on the joint user grouping and the resource block (RB) allocation algorithm for LTE uplink virtual MIMO systems. Considering the user grouping and joint resource allocation, we construct a VMIMO transmission system model. Based on this system model, we formulate maximizes the sum of system’s capacity with the system constrains, which is a complexity optimization problem. Further, to reduce the computational complexity, especially in the case of large number of users and resources, an efficient branch search algorithm using revised simplex method based on bi-direction 0-1 pivot (SM_BD0-1P) is proposed. We evaluate the proposed joint resource allocation algorithms in LTE uplink scenarios and the results show that it achieves good tradeoff between performance and complexity and has better system throughput than the existing algorithms for LTE uplink virtual MIMO systems.

Yang Cai, Shaojun Qiu, Jia Cai, Wenchi Cheng, Xiaofeng Lu

Research on UAV Swarm Interference Based on Improved Invasive Weed Optimization Algorithm

With the continuous development of Unmanned Aerial Vehicle (UAV) technology, autonomous control systems and communication technologies, the combat mode of UAV has gradually shifted from single-platform to multi-platform operation adapting to complex battlefield environment, i.e. the mode of operation has gradually developed to ‘swarm’. On this basis, UAV swarm carried jamming equipment can conduct large-scale cooperative jamming on radar. UAV swarm, with low launch power, can be deployed in the enemy depth and thus obtain the advantages of distance and spatial distribution. This paper focuses on the formation of effective cooperative jamming beams for UAV swarm. Due to the application background of UAVs, the distance between the UAV array antennas is much larger than the half-wavelength, resulting in the occurrence of grating lobes and the energy is difficult to concentrate. And the above problems are solved through sparse array synthesis, which use improved invasive weed optimization (IIWO) algorithm to optimize position of UAVs. And the simulation results show that sparse array synthesis can solve the problem of energy concentration and grating lobes.

Lijiao Wang, Yanping Liao, Xiaoming Luan

Sparse Decomposition Algorithm Based on Joint Sparse Model

Orthogonal Matching Pursuit (OMP) algorithm is the most classical signal recovery algorithm in compressed sensing. It is also applicable to the Joint Sparse Model (JSM) of distributed compressive sensing. However, OMP algorithm suffers from high computational complexity and poor anti-noise ability without considering the correlation between signals. Therefore, by combining the characteristics of the JSM-1 and JSM-2 models, we propose the corresponding joint sparse decomposition algorithms, named JSM1-OMP and JSM2-OMP. The JSM2-OMP algorithm can be viewed as improvement of the JSM1-OMP algorithm. Furthermore, a better JSM-OMP algorithm is proposed by modifying the JSM2-OMP algorithm. The simulation experiments demonstrate the effectiveness of the proposed algorithms.

Qiyun Xuan, Si Wang, Yulong Gao, Junhui Cheng

Millimeter Wave Massive MIMO Channel Estimation and Tracking

With the rapid development of 5G, massive MIMO technology has become one of the most important technologies in 5G. However, while massive MIMO technology could provide reliable performance guarantee, with the number of antennas increases, the problem of channel estimation has also become more complicated. To solve this problem, we propose a channel state estimation and tracking algorithm based on particle filter, when considering the temporal correlation between the millimeter wave narrowband block fading channels. A channel state model including channel gain, the angle of arrival, and the angle of departure has been established. A performance comparison is carried out, in terms of normalized mean square error, considering massive MIMO channel estimation, for different algorithms. We also take into account the performance affected by signal to noise ratio and the number of antennas. Numerical results show that the performance can be considerably improved in the case of a large number of antennas over the conventional scheme. Furthermore, this algorithm also has better performance under traditional MIMO conditions.

Yanwu Song, Shaochuan Wu, Wenbin Zhang, Huafeng Zhang

Deep Learning-Based Space Shift Keying Systems

To handle the performance degradation of space shift keying (SSK) systems under practical non-Gaussian channels, we propose a deep neural network model in which an auto-encoder (AE) is developed to design proper constellations and corresponding demodulation. With full knowledge of channel statistics, the transmitter and receiver are jointly optimized in our scheme. By representing the SSK system as an AE, we consider the cross-entropy loss function for antenna index and formulate the overall pipeline using deep learning techniques. Moreover, our implementation can be adopted in several noise conditions successfully. Results confirm that our model outperforms the maximum likelihood (ML) detection scheme in terms of block error rates (BLER).

Yue Zhang, Xuesi Wang, Jintao Wang, Yonglin Xue, Jian Song

Non-orthogonal Multiple Access Enabled Power Allocation for Cooperative Jamming in Wireless Networks

In this work, we investigate the non-orthogonal multiple access (NOMA) enabled power allocation for cooperative jamming under a two-user downlink scenario. In particular, we consider that there exists a malicious eavesdropper overhearing the data transmission of the mobile user (MU) with a stronger channel power gain. Meanwhile, exploiting the simultaneous transmission in NOMA, we consider that the other MU with a weak channel power gain provides cooperative jamming to the eavesdropper for enhancing the secure throughput of the stronger MU. In particular, we formulate a power allocation problem to maximize the secure throughput of the strong MU while satisfying the throughput requirement of the weak MU. Despite the non-convexity of the formulated problem, we provide an efficient algorithm to compute the optimal solution (i.e., the power allocations for the two users). Numerical results are provided to validate the effectiveness of our proposed algorithm and the performance of our optimal power allocation scheme.

Yuan Wu, Weicong Wu, Daohang Wang, Kejie Ni, Li Ping Qian, Weidang Lu, Limin Meng

Joint Time-Frequency Diversity in the Context of Spread-Spectrum Systems

We discuss a new method for realizing the diversity in spread-spectrum communications over fast-fading multipath channels. Maximum Ratio Combining (MRC) can add the synchronized tributary signals in the weighted approach to obtain the maximum diversity gain. The signal distortion caused by the Doppler shift broadened spectrum cannot be eliminated. The diversity receiver used in existing systems suffers from significant performance degradation due to the rapid channel variations encountered under fast fading. We show that the Doppler spread caused by temporal channel variations actually provides other versatile means that can be further utilized to resist fading. This paper proposes a receiving method based on time-frequency cooperative processing. Joint time-frequency representation is a powerful tool. With precise synchronization and channel estimation, even the relatively small Doppler spread encountered in practice can be used for significant diversity gains by our approach. The framework is suitable for multiple mobile wireless multiple access systems and can provide significant performance improvements over existing systems.

Qiuhan Teng, Xuejun Sha, Cong Ma

Design of Radar-Communication Integrated Signal Based on OFDM

With the development of information technology, the electromagnetic environment is becoming more and more complex, and the demand for bringing together electronic devices of different functions is urgently increasing. Among them, the radar-communication integration is a research hotspot. The current radar-communication integration research mainly focuses on the integrated signal design. Due to the similarity between OFDM signals and phase-encoding radars, it is possible to apply OFDM to radar. Aiming at the problem that the randomness of communication data affects the detection capability of OFDM radar, this paper proposes an integrated OFDM radar-communication signal design based on P4 cyclic shift code. And we verified communication BER and radar range and velocity performance for multi-target of the integrated system. The transmitting end carries out an integrated signal design that is consistent with the communication OFDM signal. The degree of system integration is high, and it achieves communication functions without reducing radar detection capability. For the high PAPR problem, we introduce CE-OFDM signals, and derive a radar signal processing algorithm based on FFT demodulation. This paper provides a theoretical basis for applications of OFDM-based integrated signals and it is an effective integrated scheme.

Tianqi Liang, Zhuoming Li, Mengqi Wang, Xiaojie Fang

A Multicast Beamforming Algorithm to Improve the Performance of Group Service for Multicell B-TrunC System

With the increasing demand for the command and dispatch service of private network communication system, broadband trunking communication (B-TrunC) system and its standards are improving steadily. In order to improve the performance of group service of B-TrunC system, we propose a system model with same-frequency multicell coordination for group users and a multicast beamforming algorithm based on the system model. The proposed system model combines multicell coordination and same-frequency scheduling. The multicast beamforming optimization problem is a non-deterministic polynomial hard (NP-hard) problem. The mathematical model of the proposed algorithm is obtained according to direction of departure (DOD) of group users and max-min fairness (MMF) principle; the optimal approximate solution of transmitting multicast beamforming weight vector, which maximizes the least received SNR of group users, is obtained on the basis of semidefinite relaxation (SDR). Theoretical analysis and simulation results show that the proposed multicast beamforming algorithm based on same-frequency multicell coordination can significantly improve the SNR of cell-edge users and increase the group user channel capacity. As the group user angle interval decreases or the base station antenna number increases, the performance of the proposed algorithm is further improved.

Zheming Zhang, Chengwen Zhang, Yutao Liu, Bin Wang

Neural Networks in Hybrid Precoding for Millimeter Wave Massive MIMO Systems

Neural networks have been applied to the physical layer of wireless communication systems to solve complex problems. In millimeter wave (mmWave) massive multiple-input multiple-output (MIMO) systems, hybrid precoding has been considered as an energy-efficient technology to replace fully-digital precoding. The way of designing hybrid precoding in mmWave massive MIMO systems by multi-layer neural networks has not been investigated. Based on further decomposing the baseband precoding matrix, an idea is proposed in this paper to map hybrid precoding structure to a multi-layer neural network. Considering the deterioration in the throughput and energy efficiency of mmWave massive MIMO systems, the feasibility of the proposed idea is analyzed. Moreover, a singular value decomposition (SVD) based decomposing (SVDDE) algorithm is proposed to evaluate the feasibility of the proposed idea. Simulation results indicate that there is an optimal number of users which can minimize the performance deterioration. Moreover, the simulation results also show that slight deterioration in the throughput and energy efficiency of mmWave massive MIMO systems is caused by further decomposing the baseband precoding matrix. In other words, further decomposing the baseband precoding matrix is a feasible way to map the hybrid precoding structure to a multi-layer neural network.

Jing Yang, Kai Chen, Xiaohu Ge, Yonghui Li, Lin Tian

A Reinforcement Learning Based Joint Spectrum Allocation and Power Control Algorithm for D2D Communication Underlaying Cellular Networks

This paper studies the spectrum allocation and power control (SA-PC) problem in device-to-device (D2D) communication underlaying a cellular network. A distributed multi-agent reinforcement learning (MARL) based joint SA-PC algorithm is proposed for performing spectrum allocation and power control for each D2D user in the network. The proposed algorithm uses Q learning, a typical form of reinforcement learning (RL), to select the optimal resource block (RB) and power level for each D2D user. In the Q-learning algorithm, each D2D user is treated as an individual agent and maintains a single-state Q table. Each agent selects an RB and a power level according to its Q table in the learning process. Simulation results show that the proposed Q-learning based joint SA-PC algorithm can achieve good throughput performance.

Wentai Chen, Jun Zheng

Improved Neural Machine Translation with POS-Tagging Through Joint Decoding

In this paper, we improve the performance of neural machine translation (NMT) with shallow syntax (e.g., POS tag) of target language, which has better accuracy and latency than deep syntax such as dependency parsing. We present three NMT decoding models (independent decoder, gates shared decoder and fully shared decoder) to jointly predict target word and POS tag sequences. Experiments on Chinese-English and German-English translation tasks show that the fully shared decoder can acquire the best performance, which increases the BLEU score by 1.4 and 2.25 points respectively compared with the attention-based NMT model.

Xiaocheng Feng, Zhangyin Feng, Wanlong Zhao, Nan Zou, Bing Qin, Ting Liu

Distance Measurement Based on Linear Phase Correlation in WiFi CSI

In this paper, we propose a new distance measurement algorithm based on WiFi Channel State Information (CSI). In order to resolve the phase error in traditional commodity WiFi devices, we design a system based on the Universal Software Radio Peripheral (USRP) with GNU Radio to analyze and separate the mixed phase errors. After the calibration of the CSI phase, it is found that the clock divider phase offset (DPO), which is introduced by the random phase offset in the clock, will affect the CSI phase, and a clustering-based method is proposed to remove the effect of DPO. We recover the linear relationships among the subcarriers phase and combine the center subcarrier phase to estimate the distance. In our algorithm, we can complete the distance measurement by using only one frequency band. Experiment results indicate that our algorithm can achieve centimeter-level accuracy in distance measurement.

Qingfei Kang, Liangbo Xie, Mu Zhou, Zengshan Tian

A Transfer Learning Method for Aircrafts Recognition

An effective method for recognizing aircrafts with different resolutions is proposed. Since training aircraft samples and test aircraft samples are imaging in different resolutions, different satellites and different imaging conditions, they obey different distributions. The Feature Subspace Alignment and Balanced Distribution Adaptation (FSA-BDA) method is proposed to solve this problem. Different from other transfer learning methods, it considers both spatial alignment and probability adaptation, so that, the probability distribution of the source domain data and the target domain data is as consistent as possible in the same feature space. The method first performs FSA, which maps the source domain and the target domain data to a low-dimensional common mapping space through different mapping matrices for preserving the structural information. Secondly, the BDA method is used to properly adapt the marginal probability and the conditional probability through the weight adjustment, which can leverage the importance of the marginal and conditional distribution discrepancies. This paper aims at recognizing three types of aircrafts, which are B52, F15 and F16 aircrafts. The experimental results show that the proposed method is better than several state-of-the-art methods.

Hongbo Li, Bin Guo, Tong Gao, Hao Chen

A New Two-Microphone Reduce Size SMFTF Algorithm for Speech Enhancement in New Telecommunication Systems

This paper considers the problem of speech enhancement and noise reduction in speech recognition systems and 5G mobile communication systems. The presence of these systems in a noisy environment reduces their effectiveness and makes degradation in their performance. here, we propose a new contribution to resolve noise reduction and speech enhancement problem in these systems by proposing a new algorithm. The proposed two microphones reduce size simplified fast transversal filter (TM-RSMFTF) algorithm is an outcome of the good combination between the well-known forward blind source separation structure and the adaptive algorithm reduce size simplified fast transversal filter properties which is a stable version of fast transversal filter (FTF) algorithms. The proposed algorithm has low computational complexity. The simulation results show a good performances and effectiveness of this new TM-RSMFTF algorithm in comparison with conventional TM-NLMS algorithm and almost similar performances with full-size TM-SFTF in terms of various objectives criteria such as Segmental SNR, System Mismatch, Segmental MSE.

Zineddine Guernaz, Xuanli Wu

Adaptive Beamforming of Vertical Frequency Diverse Array for Airborne Radar

To decouple the range-angle-dependent beampattern, a new type of frequency diverse array (FDA) with frequency increment applied across the vertical array elements is proposed, referred to as the vertical frequency diverse array (VFDA). The adaptive algorithm for the design of the receive antenna is also presented to generate a single-maximum beampattern. Simulation results verify the effectiveness. It shows that the proposed approach outperforms the multiple-input multiple-output (MIMO) radar in focusing the transmit energy on the far-field targets.

Xuzi Wu, Yongliang Sun

2D DOA Estimation of PR-WSF Algorithm Based on Modified Fireworks Algorithm

Two-dimensional direction of arrival (DOA) estimation has more application significance than one-dimensional estimation. However, the increase of computation scale causes serious problems of slow speed of solution and poor real-time performance. Among the common algorithms of two-dimensional direction of arrival (DOA) estimation, the weighted subspace fitting (WSF) algorithm possesses high accuracy, but its complexity in solving process weakens its performance advantage. In addition, the accuracy of WSF is poor under the condition of low signal-to-noise ratio (SNR) and insufficient snapshot number (i.e. threshold). Hence, this paper proposes a PR-WSF algorithm based on modified fireworks algorithm: the radius and number of explosions in fireworks algorithm are initially improved, then the ESPRIT algorithm combined with cramer-rao bound (CRB) is adopted to create a smaller searching space, and finally the pseudo-random noise resampling (PR) algorithm is introduced to improve the “threshold performance. The experimental results show that this algorithm balances the relationship between global search and local search, reduces unnecessary computation, and has better estimation performance at the threshold.

Yanping Liao, Chang Fu, Emmanuel Milambo Mung’onya

Research on Indoor and Outdoor Seamless Positioning Based on Combination of Clustering and GPS

Aiming at the key technical issue which is needed to be solved in seamless positioning, a seamless positioning algorithm based on combination of indoor joint clustering positioning and GPS is proposed in this paper. This algorithm uses GPS satellite positioning technology in outdoor environment and indoor joint clustering positioning algorithm in indoor environment, a switching algorithm is proposed to improve the smoothness of switching when it transit from indoor environment to outdoor one (and vice versa). The experimental results show that the proposed algorithm can meet the requirements of seamless positioning both indoors and outdoors better.

Jingqiu Ren, Ke Bao, Siyue Sun, Weidang Lu

Angle-of-Arrival Positioning System Based on CSI Virtual Antenna Array

Traditional Wi-Fi positioning systems usually use the signal intensity for fingerprint localization. However, the intensity of the received signal varies with time. And it is also easily affected by the indoor multipath environment. This paper presents a positioning system using Channel State Information (CSI) exposed by commodity Wi-Fi chips without any hardware adjustments. The core modules of this system include an Angle of Arrival (AOA) and Time of Flight (TOF) estimating algorithm using CSI, along with a clustering algorithm to identify the direct path in multipath environment. In this paper, we employ affine propagation clustering to avoid disadvantages of traditional K-means algorithm. The experiment results show the proposed system achieves an accuracy of about 1 m in a multipath-rich indoor environment.

Lu Yin, Ziyang Wang, Zhongliang Deng, Tianrun Jiang, Yuan Sun

Cross-Sensor Image Change Detection Based on Deep Canonically Correlated Autoencoders

Change detection for cross-sensor remote sensing images is an important research topic with a wide range of applications in disaster treatment, environmental monitoring and so on. It is a challenging problem as images from various acquisitions have difference in the spatial and spectral domains. Change detection models need effective feature representations to estimate interesting changes, but sometimes the hand-crafted low-level features affect the detection result. In this paper, we propose a novel cross-sensor remote sensing image change detection method based on deep canonically correlated autoencoders (DCCAE). The method extracts abstract and robust features of two multi-spectral images through two autoencoders, and then project them into a common latent space, in which any change detection models can be applied. Our experimental results on real datasets demonstrate the promising performance of the proposed network compared to several existing approaches.

Yuan Zhou, Hui Liu, Dan Li, Hai Cao, Jing Yang, Zizi Li

An Innovative Weighted KNN Indoor Location Technology

Aiming at the problem of large fluctuation and low precision of the positioning method based on wireless fingerprint matching, we proposed an improved weighted K nearest neighbor algorithm and compared it with the commonly used machine learning algorithm. At the same time, we designed an innovative fingerprint database construction method and a new matching strategy. We used the particle filter algorithm to realize the fusion of the fingerprint matching localization algorithm and the pedestrian dead reckoning (PDR) algorithm, and eliminated the outliers, thus improving the positioning accuracy. The experimental results show that the average positioning accuracy after fusion is 0.512 m, and the positioning error within 1 m is 93.88%. It satisfies the accuracy requirements of indoor positioning and also verifies the effectiveness of the algorithm.

Lu Huang, Xingli Gan, Dan Du, Boyuan Wang, Shuang Li

A Resistance Frequency Offset Synchronization Scheme Based on the Zadoff-Chu Conjugate Sequence

Zadoff-Chu (ZC) sequences have been used as synchronization sequences in many wireless communication systems because of their perfect correlation properties. However, almost all of these ideal characteristics are based on the assumption of zero carrier frequency offset (CFO). Under large frequency offset circumstances, the perfect autocorrelation property of ZC sequence is destroyed, where the main correlation peak is decreasing while the vice peak is increasing, consequently degrading the timing performance. In this paper, the autocorrelation of the ZC sequence and its conjugate sequence are investigated, and the symmetry between the modulus values of their autocorrelation functions is developed as well. Taking advantage of this symmetry, a novel training sequence composed of ZC sequence and ZC conjugate sequence is proposed. Also proposed is a corresponding synchronization scheme enabling robust timing synchronization based on the ZC sequence and ZC conjugate sequence at the receiver in the presence of large CFO.

Cong Ma, Xuejun Sha, Yong Li, Xu Lin

AI-Based Medium Access Control

Frontmatter

Compressed Sensing ISAR 3D Imaging Methods Based on OMP Algorithm

In the application of three-dimensional imaging inverse synthetic aperture radar, the existing matching tracking-based compression tracking reconstruction algorithm has many problems, such as large computer storage and low computational efficiency. Based on the Orthogonal Matching Pursuit (OMP) algorithm, this paper proposes a dimensionality-compressive sensing reconstruction method Kron OMP based on the sparseness of the Inverse-Synthetic-Aperture-Radar (ISAR) target and the three-dimensional separability of the perceptual matrix. Firstly, a three-dimensional ISAR imaging model is established, and the Kronecker product expression method is used to split the perceptual matrix and transform the 3D reconstruction into a two-dimensional reconstruction problem. Comparing the time and memory consumption of the algorithm, the Kron OMP algorithm reduces the computer memory requirements of the perceptual matrix by more than 95% during the reconstruction process and reduces the computation time by more than 90%. Simulation experiments verify the effectiveness of the algorithm.

Jingcheng Zhao, Zongkai Yang, Shaozhu Gu

Ambiguity Function Analysis of Radar-Communication Integrated Waveform Based on FDM and TDM Technologies

In this letter, we propose a novel radar-communication integration signal, which employs the linear frequency modulation (LFM) signal modulated by digital symbols is divided from time and frequency domain to achieve radar detection and data communication. By analyzing its ambiguity function, we confirm its feasibility of applying in radar-communication integration system.

Hongzhi Men, Zhiqun Song, Guisheng Liao

Transmission Quality Improvement Algorithms for Multicast Terrestrial-Satellite Cooperation System

In this paper, we investigate a terrestrial-satellite multicast beamforming cooperative system to optimize the problem of low expenses and high capacity requirements of ground users. Different from the point-to-point link-based terrestrial network, we design the terrestrial and satellite beamforming vectors cooperatively based on the required contents of users in order to realize more reasonable resource allocation. The satellite and base stations provide service cooperatively for ground users within coverage, and during transmission, both the satellite and the base stations use the multicast beamforming technique to improve the system performance, and the user group scheduling, resource allocation and beamforming design are considered jointly. Based on this architecture, we first formulate a joint optimization problem to maximize the system capacity performance, and we design the beamforming vectors of the base stations and the satellite cooperatively on the basis of user group scheduling and power constraints. Then we extend the problem into a more realistic scene that the link delay of satellite is larger than it of base stations, this may influence the joint optimization timeliness of condition changes. So we propose a two phases optimization algorithm that we optimize terrestrial-satellite system jointly in the first phase and optimize terrestrial part independently in the second phase. The simulation results show that, the proposed algorithm gains more than 38% of capacity improvement compared with maximum ratio transmission (MRT) method.

Yuandong Zhang, Liuguo Yin

Application of Wavelet Analysis Method in Radar Echo Signal Detection

In this paper, we focus on several signal detection method and wavelet analysis method for radar echo signal detection. According to the characteristics of signal detection and modern signal processing theory, we have deduced and analyzed the principles of these algorithms in mathematics, which involves more profound knowledge such as higher-order statistics and wavelet, and of course. It is important that we perform wavelet analysis on the echo signals of the HF ground wave radar to remove the weak ionospheric clutter and the method performs well. Wavelet is an important mathematical application method in signal detection.

Qiuyue Li, Xiangyu Tong

Chinese News Keyword Extraction Algorithm Based on TextRank and Topic Model

TextRank tends to choose frequent words as keywords of a document. In fact, some infrequent words can also be keywords. In order to improve this situation, a Chinese news keyword extraction algorithm LDA-TextRank based on TextRank and LDA topic model is proposed. The algorithm is a single document, unsupervised algorithm. It defines the diffusivity of two candidate words, constructs a new weight formula, and improves the weight of the edges in the text graph. At the same time, it combines with the LDA topic model, and the damping factor in TextRank is adjusted by calculating the word’s topic relevance of the document. The experiment was carried out on the Chinese corpus. The results show that compared with TextRank, LDA-TextRank has an improvement in Precision, Recall and F1-measure.

Ao Xiong, Qing Guo

An Adaptive Threshold Decision Algorithm in Non-cooperative Signal Detection

As the communication environment becomes more and more complex, it becomes more meaningful to detect and capture useful signals accurately. In this paper, we mainly focus on several typical burst signal detection algorithms in wireless communication networks. We analyze the signal energy detection algorithm, preamble detection, and frequency domain detection algorithms, then perform simulations for them. Above these, responding to non-cooperative communications, an adaptive threshold decision algorithm based on projection method is designed. Finally, we come to a conclusion, that each algorithm is suitable for burst signal detection, having its own advantages and disadvantages in different environments. And our decision algorithm is effective.

Ziheng Li, Shuo Shi, Xuemai Gu

Trajectory Optimization Under Constrained UAV-Aided Wireless Communications with Ground Terminals

Using the unmanned aerial vehicles (UAV) to form a communication platform is of great practical significance in future wireless networks. This article investigates the flight trajectory optimization problem with minimum energy consumption when the UAVs are mobile servers and communicate with the ground terminals (GT). The proposed trajectory considers the features of conventional paths as well, i.e., the channel quality and energy saving. Numerical results show that our approach outperforms the other schemes in terms of the throughput of data and the features of the UAV.

Kun Chen, Hong Lu, Xiangping Bryce Zhai, Congduan Li, Yunlong Zhao, Bing Chen

IOT-Based Thermal Comfort Control for Livable Environment

Thermal Comfort Control for indoor environment is an important issue in smart city since it is benefit to people’s health and helps to maximize their working productivity and provide a livable environment. In this paper, we present an IOT (Internet of Things) based personal thermal comfort model with automatic regulation. This model employs some environment sensors such as temperature sensor, humidity sensor, etc., to continuously obtain the general environmental measurements. Specially, video cameras are also integrated into the IOT network of sensors to capture the individual’s activity and dressing condition, which are important factors affecting one’s thermal sensation. The individual’s condition image can be mapped into different metabolic rates and different clothing insulations by machine learning classification algorithm. Then, all the captured or converted data are fed into a PMV (Predicted Mean Vote) model to learn the individual’s thermal comfort level. In the prediction stage, we introduce the cuckoo search algorithm to solve the air temperature and air velocity with the learnt thermal comfort level, which is convergent rapidly. Our experiments demonstrate that the metabolic rates and clothing insulation have great effect on personal thermal comfort, and our model with video capture helps to obtain the variant values regularly, thus maintains the individual’s thermal comfort balance in spite of the variation of activity or clothing.

Miao Zang, Zhiqiang Xing, Yingqi Tan

Context Adaptive Visual Tracker in Surveillance Networks

CNN-based visual trackers has been successfully applied to surveillance networks. Some trackers apply sliding-window method to generate candidate samples which is the input of network. However, some candidate samples containing too much background regions are mistakenly used for target tracking, which leads to a drift problem. To mitigate this problem, we propose a novel Context Adaptive Visual tracker (CAVT), which discards the patches containing too much background regions and constructs a robust appearance model of tracking targets. The proposed method first formulates a weighted similarity function to construct a pure target region. The pure target region and the surrounding area of the bounding box are used as a target prior and a background prior, respectively. Then the method exploits both the target prior and background prior to distinguish target and background regions from the bounding box. Experiments on a challenging benchmark OTB demonstrate that the proposed CAVT algorithm performs favorably compared to several state-of-the-art methods.

Wei Feng, Minye Li, Yuan Zhou, Zizi Li, Chenghao Li

Research on Indoor Localization Based on Joint Coefficient APIT

The APIT algorithm has become a popular technology for indoor localization due to its simplicity and low power consumption. However, the APIT algorithm often has misjudgments of In-to-Out in practical applications. And a large number of nodes cannot be located, when the density of anchor nodes (AN) is low. For this, this paper proposes a joint coefficient triangle APIT localization algorithm (JCTA). First, an effective triangle decision method is proposed. Then, the RSSI localization, the maximum likelihood method, and the weighted triangular coordinate calculation method are introduced and combined. Finally, an iterative co-location idea is used to locate the pending node (NP). The simulation results show that the JCTA algorithm can show good performance in terms of localization coverage rate and localization error about nodes.

Min Zhao, Danyang Qin, Ruolin Guo, Lin Ma

A Cross-Layer Approach to Maximize the Lifetime of Underwater Wireless Sensor Networks

Efficient usage energy of sensors can lead to prolonged lifetime in underwater wireless sensor networks (UWSNs). This paper addresses maximization of the network lifetime for UWSNs. More specifically, it considers an optimal cross-layer design of transmission schemes. Here we restrict ourselves to the type of time division multiple access schedules in the link layer. In order to balance energy consumption over different nodes, we develop a Mixed Integer Non-Linear Programming formulation to facilitate joint optimization of link schedules, transmission powers and rates of sensors. We have also conducted extensive network simulations to test the proposed algorithm. The results confirm that our approach can prolong overall network lifetime.

Yuan Zhou, Hui Liu, Hai Cao, Dan Li, Hongyu Yang, Tao Cao

An Efficient Indoor Localization Method Based on Visual Vocabulary

This paper proposes a new efficient indoor localization method based on visual vocabulary. The special feature of this method is that no additional components are needed, but only mobile devices equipped with cameras. By matching the query image with a visual vocabulary constructed by a Bag of Self-Optimized-Ordered Visual Vocabulary (BoSOV), the user’s position can be accurately determined. In addition, the efficiency of our scheme is compared with that of other schemes, and simulation results reveal that our method has higher indoor positioning efficiency, especially when the amount of image data is large. Simulation results show that our method can well achieve efficient visual indoor positioning when the data volume is relatively large.

Ruolin Guo, Danyang Qin, Min Zhao, Guangchao Xu

Realization and Performance Simulation of Spectrum Detection Based on Cyclostationarity Properties

With the wide application of radio technology, spectrum resources are becoming more and more important. Cognitive radio is a new subject that is used to make full use of spectrum resources. The paper studies the spectrum sensing in cognitive radio and focuses on non-cooperative detection method. Based on the energy detection and analysis of the principle of feature detection in periodic stationary process. Using MATLAB for simulation analysis, making comparison of performance between the two methods. The detection performance of the periodic stationary process feature method is 5–7 dB better than the energy detection performance. And the system overhead is about an order of magnitude higher than energy detection.

Zhiqun Song, Yujing Lv, Zhongzhao Zhang

AI-Enabled Network Layer Algorithms and Protocols

Frontmatter

An Improved TDoA Localization Algorithm Based on AUV for Underwater Acoustic Sensor Networks

Now localization is one of the major issues in underwater environment work. In terrestrial application, time different of arrival (TDoA) localization algorithm has been widely used. However, most localization systems rely on radio or optical signals while they cannot propagate well in water. Therefore, with complicated environment in underwater acoustic sensor networks (UASNs), traditional TDoA localization algorithm suffers various unstable factors, such as they can only work in a finite region or need clock synchronization. In this paper, we propose an improved TDoA localization algorithm (ITLA) based on AUV for UASNs. The mobile AUV first finds its own accurate three-dimensional coordinates in the surface with the help of GPS or other terrestrial location systems. Then we deployed AUV at predefined depth in underwater as reference nodes. AUV periodically sends packets with coordinates information to unlocalized nodes in different positions. After receiving data and a series of calculation, we quantify the conditions for unique localization and propose another condition to evaluate the reliability of results. This algorithm can achieve relatively higher accuracy with relatively smaller calculation and overcome some traditional localization drawbacks. We demonstrate the trade-offs between location coverage, the cost in placing reference nodes, and energy consumption.

Kaicheng Yu, Kun Hao, Cheng Li, Xiujuan Du, Beibei Wang, Yonglei Liu

Fuzzy Probabilistic Topology Control Algorithm for Underwater Wireless Sensor Networks

Aiming at the problem that the underwater wireless sensor network is limited in energy and the underwater topology is susceptible to the dynamic environment, this paper designs an AUV-assisted fuzzy probability power topology control (FPPTC) algorithm by introducing AUV nodes and clusters generated by clustering. Head node communication reduces power consumption of low energy nodes. According to the data deviation value between the current data value of the AUV node and the target parameter, the adjustment probability of the transmission power is determined, and the transmission power of the AUV node is adjusted to an optimal value to reduce the underwater topology energy consumption, prolong the network life cycle, and improve the network. The purpose of communication quality. The simulation results show that the FPPTC algorithm can improve network coverage, slow down node failure speed and extend network life cycle.

Wenhao Ren, Kun Hao, Cheng Li, Xiujuan Du, Yonglei Liu, Li Wang

Naive Bayes Classifier Based Driving Habit Prediction Scheme for VANET Stable Clustering

Vehicular ad hoc networks (VANETs) is a promising network form for future application on road, like arriving automatic driving and in-vehicle entertainment. Compare with traditional mobile ad hoc networks (MANETs), its advantages are multi-hop communication without energy restriction and relative regular moving pattern. However, the high mobility of nodes raises many challenges for algorithm designers such as topology changing, routing failures, and hidden terminal problem. Clustering is an effective control algorithm provides efficient and stable routes for data dissemination. Efficient clustering algorithms became challenging issues in this kind of distributed networks. In this paper, a novel machine learning based driving habit prediction scheme for stable clustering is proposed, briefly named NBP. In the scheme, vehicles are divided into two alignments with opposite driving habit from which stable cluster design could benefit. Naive Bayes classifier is introduced to estimate the alignment of vehicles by several factors, such as relative speed, vehicle type, number of traffic violations and commercial vehicle or not. Combined with clustering design, the proposed method has been proven effective for stable clustering in VANET.

Tong Liu, Shuo Shi, Xuemai Gu

Path Optimization with Machine-Learning Based Prediction for Wireless Sensor Networks

The trajectory scheduling of the mobile nodes is a critical research problem in rechargeable wireless sensor networks. In this paper, we propose a machine-learning based energy consumption prediction (ML-ECP) approach, which uses machine-learning to predict the energy consumption rates in wireless sensor networks. Based on the prediction, the sensor nodes are partitioned into multiple clusters and the optimal trajectories are obtained for mobile nodes. We compare the proposed approach with the existing approach, the results show that the ML-ECP improves the energy efficiency for sensor nodes recharging and data collection, and the mobile nodes collect information and recharge sensor nodes periodically in the network.

Jianxin Ma, Shuo Shi, Xuemai Gu

Research on the Maximization of Total Information Rate Based on Energy Allocation in Multi-user SWIPT Relaying System

With the rapid development and wide application of the wireless communication network, the communication network based on the simultaneous wireless information and power transfer (SWIPT) technology has attracted more and more extensive research. This technology solves the problem of frequent charging or replacement of the device battery very well, has greatly extended the working hours of the device, and can be adapted to some special communication environments such as high temperature and high pressure. This paper studies the effect of the energy allocation in multi-user SWIPT relaying system on the information rate. Thereinto, the relay uses the energy harvested in the energy harvesting mode to amplify and forward the information of the users. The total information rate maximization model is proposed and the corresponding energy allocation scheme is derived. The simulation results show that the proposed energy allocation scheme can maximize the total information rate of all users.

Jianxiong Li, Xuelong Ding, Xianguo Li, Kunlai Li, Ke Zhao, Weiguang Shi

Optimization of AODV Routing Protocol in UAV Ad Hoc Network

According to high-speed mobile nodes in unmanned aerial vehicles (UAV) Ad Hoc network to bring the network topology changes frequently, link time is short, and node energy is limited, this paper puts forward an optimized AODV protocol (EV-AODV) based on residual energy and relative movement speed of nodes. Simulation results show that EV-AODV routing protocol proposed improves the packet delivery ration and network life time compared with traditional AODV protocols. It is better suitable for the networks environment with UAV Ad Hoc network.

Jianze Wu, Shuo Shi, Zhongyue Liu, Xuemai Gu

A KFL-TDOA UWB Positioning Method Based on Hybrid Location Algorithm

For the improvement of accuracy and efficiency of indoor positioning in complex environment, this paper proposed a new positioning method, which combined Ultra-Wide Band (UWB) based on time difference of arrival (TDOA) with linearized Kalman filters (KFL-TDOA), in order to obtain more accurate and stable positioning results. On this basis, two classic location algorithms, Chan and Taylor series expansion algorithm, were integrated to get lower Root Mean Square Error (RMSE) and better anti-interference performance under non-sight-of-light (NLOS) and multipath effect, compared with using them separately. The proposed method considered interference both in ranging phase and positioning phase caused by complex indoor environment. Simulation case studies were conducted to demonstrate how the proposed method was implemented and the simulation results showed that compared with traditional TDOA based positioning method, the proposed method has improvement in positioning accuracy and stability both in ideal environment and interference environment if the parameters were set reasonable.

Shuo Shi, Meng Wang, Kunqi Hong

Simultaneous Wireless Information and Power Transfer Protocol Under the Presence of Node Hardware Impairments

Hardware impact to the wireless sensor network node can reduce the life cycle and communication quality of the energy harvesting network. In this paper, we use a three-node network communication model to derive the exact closed form and asymptotic expression of the outage probability and through the Rayleigh fading channel. Then, we study the outage probability and throughput of the wireless sensor network from the hardware impact of the source node and the destination node. In addition, we provide numerical results to demonstrate the correctness of the simulation. The hardware impact of the node physical transceiver is unavoidable, but we can minimize the impact on the network by selecting configuration parameters, which is of great significance to engineering practice.

Yanlin Liu, Juan Li, Fengye Hu, Qiao Qiao

An Improved A* Algorithm Based on Divide-and-Conquer Method for Golf Unmanned Cart Path Planning

Path planning based on A* algorithm has been widely used in various engineering projects, but the time cost of A* algorithm for large-scale road networks is expensive, which is proportional to the square of node N. This paper proposes an improved A* algorithm based on the divide-and-conquer method for the golf unmanned cart path planning requirements, which splits the global optimal path into several local optimal paths and greatly reduces the time cost of the traditional A* algorithm with the more data space needs. Experiment results show that the proposed algorithm can decrease the time cost by at least 46% compared with the traditional A* algorithm. The real-time performance is stronger and the global optimizing path is smoother.

Yi Chen, Liangbo Xie, Wei He, Qing Jiang, Junxing Xu

Power Allocation Method for Satellite Communication Based on Network Coding

With the development of aerospace technology, more and more application tasks require satellite communications for information transmission. In space communication, the resources on the star are very precious, and it is particularly urgent to improve the utilization of resources on the star. The application of network coding in satellite communication can not only solve the traditional routing problem, but also greatly improve the reliability and efficiency of communication. So the power allocation method on satellite based on network coding is proposed. Two power allocation algorithms can improve the utilization of inter-satellite resources, and the network coding of relay nodes can reduce the bit error rate and the packet loss rate of the communication system. The simulation results show that network coding can reduce the bit error rate of the system and the impact of different power allocation algorithms on the bit error rate of the system.

Jin Liu, Zhuoming Li, Gongliang Liu

Seamless Positioning and Navigation System Based on GNSS, WIFI and PDR for Mobile Devices

As the rapid development of mobile Internet, many location-based services (LBS) have emerged for commercial cooperation, entertainment, security, and so forth. All of these require accurate and real time positioning of mobile devices with seamless indoor-outdoor transition in high dense urban regions. While satisfactory outdoor location services are achieved based on the global navigation satellite system (GNSS) technology, a really ubiquitous location system for both indoor and outdoor scenarios is not yet available. To cope with this challenge, we propose a hybrid location system, which makes the best of WIFI reference signal strength index (RSSI) fingerprinting technique for indoor positioning, traditional GNSS for the outdoor positioning, and pedestrian dead reckoning (PDR) technology for supplement. An environment-adaptive positioning handover module is proposed to perform positioning technology switching as environment changes. Moreover, a novel algorithm based on continuous hidden Markov model (CHMM) is proposed for the navigation in the indoor regions. Extensive tests for the seamless system proposed have been performed with satisfactory results and effectiveness.

Yuanfeng Du, Dongkai Yang

Adaptive Routing Protocol for Underwater Wireless Sensor Network Based on AUV

Underwater Wireless Sensor Networks (UWSNs) have the characteristics of high energy consumption, low transmission rate, and narrow bandwidth. How to extend the lifespan of UWSNs is a research hotspot of underwater routing protocols. An adaptive routing protocol (ARPA) based on autonomous underwater vehicle (AUV) is proposed in this paper. In the phase of network layering, ARPA takes AUV as the sink node to dynamically layer the network. In the data transmission stage, the next hop forwarding node that meets the requirements is selected based on the horizontal and vertical mechanism. In this paper, the ARPA is verified by the network simulator NS-3. The simulation results show that compared with the existing underwater routing protocols, the ARPA not only guarantees the efficient and stable data transmission rate but also reduces the network delay and improves the energy utilization rate.

Yuying Ding, Cheng Li, Kun Hao, Xiujuan Du, Lu Zhao, Qi Liu

Performance Analysis of Energy-Efficient Cell Switch off Scheme for CoMP Networks

In this paper, a joint power and subcarrier optimization problem to minimize the network energy consumption with considerations of dynamic Coordinated Multipoint Transmission (CoMP) clustering, user quality of service (QoS) requirement and base station (BS) load is formulated for cell switch off in CoMP transmission scenario. Since the complexity of such optimization problem is prohibitive in practical application, following the manner of dynamic programming (DP), the original problem is decomposed to a sequence of sub-problems on cell switch off with dynamic CoMP clustering and system transmit power optimization. Then the Cluster Load Search, User Sum SINR and Cell Sum Load Based Clustering Schemes are proposed for cell switch off evaluation. The simulation results show that the proposed schemes achieve competitive network energy-efficient performance compared with benchmark optimization scheme while at the same time save up to 40% of the overall overhead.

Fei Ding, Yan Lu, Jialu Li, Ruoyu Su, Dengyin Zhang, Hongbo Zhu

An Energy-Efficient Routing Protocol for Internet of Underwater Things

By using underwater acoustic sensor networks (UWSNs) as a backbone, Internet of Underwater Things (IoUT) have developed rapidly due to their applications, such as environmental monitoring, marine resources development, and geological oceanography. Frequently changing or recharging the batteries of underwater sensor nodes may not be realistic due to the harsh marine environment and high cost of underwater equipment. In this paper, we propose an energy-efficient routing protocol for IoUT for marine environmental monitoring. Our simulation results show that the proposed routing protocol can prolong the network lifetime for IoUT compared with other published routing protocols.

Ruoyu Su, Fei Ding, Dengyin Zhang, Hongbo Zhu, Xiaohong Wang

Backmatter

Additional information

Premium Partner

    Image Credits